# keras-unet-collection
[![PyPI version](https://badge.fury.io/py/keras-unet-collection.svg)](https://badge.fury.io/py/keras-unet-collection)
[![PyPI license](https://img.shields.io/pypi/l/keras-unet-collection.svg)](https://pypi.org/project/keras-unet-collection/)
[![Maintenance](https://img.shields.io/badge/Maintained%3F-yes-green.svg)](https://github.com/yingkaisha/keras-unet-collection/graphs/commit-activity)
The `tensorflow.keras` implementation of U-net, V-net, U-net++, R2U-net, Attention U-net, ResUnet-a, U^2-Net, and UNET 3+ with optional ImageNet-trained backbones.
----------
`keras_unet_collection.models` contains functions that configure keras models with hyper-parameter options.
* Pre-trained ImageNet backbones are supported for U-net, U-net++, Attention U-net, and UNET 3+.
* Deep supervision is supported for U-net++, UNET 3+, and U^2-Net.
* See the [User guide](https://github.com/yingkaisha/keras-unet-collection/blob/main/examples/user_guid_models.ipynb) for other options and use cases.
| `keras_unet_collection.models` | Name | Reference |
|:---------------|:----------------|:----------------|
| `unet_2d` | U-net | [Ronneberger et al. (2015)](https://link.springer.com/chapter/10.1007/978-3-319-24574-4_28) |
| `vnet_2d` | V-net (modified for 2-d inputs) | [Milletari et al. (2016)](https://arxiv.org/abs/1606.04797) |
| `unet_plus_2d` | U-net++ | [Zhou et al. (2018)](https://link.springer.com/chapter/10.1007/978-3-030-00889-5_1) |
| `r2_unet_2d` | R2U-Net | [Alom et al. (2018)](https://arxiv.org/abs/1802.06955) |
| `att_unet_2d` | Attention U-net | [Oktay et al. (2018)](https://arxiv.org/abs/1804.03999) |
| `resunet_a_2d` | ResUnet-a | [Diakogiannis et al. (2020)](https://doi.org/10.1016/j.isprsjprs.2020.01.013) |
| `u2net_2d` | U^2-Net | [Qin et al. (2020)](https://arxiv.org/abs/2005.09007) |
| `unet_3plus_2d` | UNET 3+ | [Huang et al. (2020)](https://arxiv.org/abs/2004.08790) |
----------
` keras_unet_collection.base` contains functions that build the base architecture (i.e., without model heads) of Unet variants for model customization and debugging.
| ` keras_unet_collection.base` | Notes |
|:-----------------------------------|:------|
| `unet_2d_base`, `vnet_2d_base`, `unet_plus_2d_base`, `r2_unet_2d_base`, `att_unet_2d_base`, `resunet_a_2d_base`, `u2net_2d_base`, `unet_3plus_2d_base` | Functions that accept an input tensor and hyper-parameters of the corresponded model, and produce output tensors of the base architecture. |
----------
`keras_unet_collection.activations` and `keras_unet_collection.losses` provide additional activation layers and loss functions.
| `keras_unet_collection.activations` | Name | Reference |
|:--------|:----------------|:----------------|
| `GELU` | Gaussian Error Linear Units (GELU) | [Hendrycks et al. (2016)](https://arxiv.org/abs/1606.08415) |
| `Snake` | Snake activation | [Liu et al. (2020)](https://arxiv.org/abs/2006.08195) |
| `keras_unet_collection.losses` | Name | Reference |
|:----------------|:----------------|:----------------|
| `dice` | Dice loss | [Sudre et al. (2017)](https://link.springer.com/chapter/10.1007/978-3-319-67558-9_28) |
| `tversky` | Tversky loss | [Hashemi et al. (2018)](https://ieeexplore.ieee.org/abstract/document/8573779) |
| `focal_tversky` | Focal Tversky loss | [Abraham et al. (2019)](https://ieeexplore.ieee.org/abstract/document/8759329) |
| `triplet_1d` | Semi-hard triplet loss (experimental) | |
| `crps2d_tf` | CRPS loss (experimental) | |
# Installation and usage
```pip install keras-unet-collection```
```python
from keras_unet_collection import models
# e.g. models.unet_2d(...)
```
* **Note**: Currently supported backbone models are: `VGG[16,19]`, `ResNet[50,101,152]`, `ResNet[50,101,152]V2`, `DenseNet[121,169,201]`, and `EfficientNetB[0-7]`. See [Keras Applications](https://keras.io/api/applications/) for details.
* **Note**: This package is planned for major updates. For versions prior to 0.1.0, backward compatibility is not ensured.
* **Note**: Neural networks produced by this package may not be compatible with other pre-trained models of the same name. Training from scratch is recommended.
* Jupyter notebooks are provided as [examples](https://github.com/yingkaisha/keras-unet-collection/tree/main/examples):
* Attention U-net with VGG16 backbone [[link]](https://github.com/yingkaisha/keras-unet-collection/blob/main/examples/human-seg_atten-unet-backbone_coco.ipynb).
* UNET 3+ with deep supervision and classification guided module [[link]](https://github.com/yingkaisha/keras-unet-collection/blob/main/examples/segmentation_unet-three-plus_oxford-iiit.ipynb).
* [Changelog](https://github.com/yingkaisha/keras-unet-collection/blob/main/CHANGELOG.md)
# Dependencies
* TensorFlow 2.3.0, Keras 2.4.0, Numpy 1.18.2.
* (Optional for examples) Pillow, matplotlib, etc.
# Overview
U-net is a convolutional neural network with encoder-decoder architecture and skip-connections, loosely defined under the concept of "fully convolutional networks." U-net was originally proposed for the semantic segmentation of medical images and is modified for solving a wider range of gridded learning problems.
U-net and many of its variants take three or four-dimensional tensors as inputs and produce outputs of the same shape. One technical highlight of these models is the skip-connections from downsampling to upsampling layers, which benefit the reconstruction of high-resolution, gridded outputs.
# Contact
Yingkai (Kyle) Sha <<yingkai@eoas.ubc.ca>> <<yingkaisha@gmail.com>>
# License
[MIT License](https://github.com/yingkaisha/keras-unet/blob/main/LICENSE)
没有合适的资源?快使用搜索试试~ 我知道了~
keras-unet-collection:Tensorflow,Keras U-net,V-net,U-net ++,R2U-...
共28个文件
py:19个
ipynb:4个
md:2个
5星 · 超过95%的资源 需积分: 50 39 下载量 195 浏览量
2021-05-07
16:05:19
上传
评论 7
收藏 257KB ZIP 举报
温馨提示
keras-unet-collection 所述tensorflow.keras实施U型网,V-净,U-净++,R2U网,注意力U形网,ResUnet-A,U ^ 2-Net和UNET 3+具有可选ImageNet训练有素骨架。 keras_unet_collection.models包含使用超参数选项配置keras模型的函数。 U-net,U-net ++,Attention U-net和UNET 3+支持预训练的ImageNet主干。 U-net ++,UNET 3+和U ^ 2-Net支持深度监督。 有关其他选项和用例,请参见《 》。 keras_unet_collection.models 名称 参考 unet_2d 网络 vnet_2d V-net(为2-d输入修改) unet_plus_2d U网++ r2_unet_2d R2U网 att
资源详情
资源评论
资源推荐
收起资源包目录
keras-unet-collection-main.zip (28个子文件)
keras-unet-collection-main
keras_unet_collection
backbones.py 991B
_model_u2net_2d.py 21KB
_model_unet_plus_2d.py 14KB
_model_att_unet_2d.py 14KB
base.py 585B
_model_resunet_a_2d.py 13KB
utils.py 2KB
_model_unet_2d.py 13KB
__init__.py 1B
models.py 545B
losses.py 8KB
_model_vnet_2d.py 10KB
layer_utils.py 15KB
activations.py 2KB
_model_unet_3plus_2d.py 18KB
_model_r2_unet_2d.py 12KB
_backbone_zoo.py 5KB
requirements.txt 68B
__init__.py 0B
examples
segmentation_unet-three-plus_oxford-iiit.ipynb 152KB
human-seg_atten-unet-backbone_coco.ipynb 156KB
user_guid_models.ipynb 20KB
LICENSE 1KB
setup.py 853B
README.md 6KB
user_guid.ipynb 19KB
.gitignore 2KB
CHANGELOG.md 2KB
共 28 条
- 1
CodeWizardess
- 粉丝: 15
- 资源: 4691
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功
评论1